© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 25-TRANSCODER-HP
    7. 108013
    Prev
    Next
    INDEX
    Explanations

    EU

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_25.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.25.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    bucks
    -0.29
    bite
    -0.28
    iquement
    -0.27
    uous
    -0.27
    abouts
    -0.27
    åĽ½ç±į
    -0.26
    аÑĨион
    -0.26
     ara
    -0.26
    odont
    -0.26
    comings
    -0.26
    POSITIVE LOGITS
    yas
    0.29
    alis
    0.28
    æĶ¹åĪ¶
    0.25
     whites
    0.25
    yal
    0.25
    zers
    0.24
     cath
    0.23
     univers
    0.23
     forces
    0.23
    ADER
    0.23
    Activations Density 0.994%

    No Known Activations